Hazem Hesham Yousef Shalby — accepted AI-conference papers

2026

DQT: Dynamic Quantization Training via Dequantization-Free Nested Integer Arithmetic

Hazem Hesham Yousef Shalby, Fabrizio Pittorino, Francesca Palermo, Diana Trojaniello, Manuel Roveri

AAAI 2026technical

The deployment of deep neural networks on resource-constrained devices relies on quantization. While static, uniform quantization applies a fixed bit-width to all inputs, it fails to adapt to their varying complexity. Dynamic, instance-based mixed-precision quantization promises a superior accuracy-

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

InfoQ: Mixed-Precision Quantization via Global Information Flow

Mehmet Emre Akbulut, Hazem Hesham Yousef Shalby, Fabrizio Pittorino, Manuel Roveri

AAAI 2026technical

Mixed-precision quantization (MPQ) is crucial for deploying deep neural networks on resource-constrained devices, but finding the optimal bit-width for each layer represents a complex combinatorial optimization problem. Current state-of-the-art methods rely on computationally expensive search algori

Cited by 3 Source ↗PDF ↗Scholar ↗